DescriptionContent-based image retrieval (CBIR) systems allow for retrieval of images from a database that are similar in visual content to a query image. This is particularly useful in scenarios such as digital pathology, where text-based descriptors alone might be inadequate to accurately describe image content. By representing images via a set of quantitative image descriptors, the similarity between a query image with respect to archived, annotated images in a database can be computed and the most similar images retrieved. Recently, non-linear dimensionality reduction (NLDR) methods have become popular for embedding high dimensional data into a reduced dimensional space while preserving local object adjacencies, thereby allowing for object similarity to be determined more accurately in the reduced dimensional space. However, most dimensionality reduction (DR) methods implicitly assume, in computing the reduced dimensional representation, that all features are equally important. Erroneous or noisy features could potentially result in dissimilar images being mapped close to each other in the reduced embedding space. In this work we present Boosted Spectral Embedding (BoSE), a variant of the traditional Spectral Embedding (SE) NLDR method, which unlike SE utilizes a boosted distance metric (BDM) to selectively weight individual features to subsequently map the data into a reduced dimensional space. In this work BoSE is evaluated against SE (which employs equal feature weighting) in the context of CBIR of digitized prostate and breast cancer histopathology images. Across 154 hematoxylin and eosin (H&E) stained histopathology images corresponding to benign and malignant prostate cancer biopsy images, low and high grade ER+ breast cancer studies, and HER2+ breast cancer H&E images, BoSE outperformed SE both in terms of CBIR-based (area under the precision recall curve) and classifier-based (classification accuracy) performance measures. Consistent trends were observed when embedding the data into spaces with different dimensions. Our results suggest that BoSE could serve as an important tool for CBIR and classification of high dimensional biomedical data.