Concavity trees are well-known abstract structures. This paper proposes a new shape-based image retrieval method based on concavity trees. The proposed method has two main components. The first is an efficient (in terms of space and time) contour-based concavity tree extraction algorithm. The second component is a recursive concavity-tree matching algorithm that returns a distance between two trees. We demonstrate that concavity trees are able to boost the retrieval performance of two feature sets by at least 15% when tested on a database of 625 silhouette images.