This paper presents a strategy for content-based image retrieval. It is based on a meaningful segmentation procedure that can provide proper distributions for matching via the Earth mover's distance as a similarity metric. The segmentation procedure is based on a hierarchical watershed-driven algorithm that extracts automatically meaningful regions. In this framework, the proposed robust feature extraction plays a major role along with a novel region weighting for enhancing feature discrimination. Experimental results demonstrate the performance of the proposed strategy.