The Cancer Genome Atlas (TCGA) provides a rich repository of whole mount tumor sections that are collected from different laboratories. However, there are a significant amount of technical and biological variations that impede analysis. We have developed a novel approach for nuclear segmentation in histology sections, which addresses the problem of technical and biological variations by incorporating information from manually annotated reference patches with the local color space of the original image. Subsequently, the problem is formulated within a multi-reference graph cut with geodesic constraints. This approach has been validated on manually curated samples and then applied to a dataset of 440 whole mount tissue sections, originating from different laboratories, which are typically 40k-by-40k pixels or larger. Segmentation results, through a zoomable interface, and extracted morphometric data are available at: http://tcga.lbl.gov.