We propose a knowledge representation approach to the semantic retrieval by content of graphics described in Scalable Vector Graphics (SVG), the novel XML based W3C approved standard language for describing two-dimensional graphics. The approach is based on a description logic devised for the semantic indexing and retrieval of complex objects. We provide a syntax to describe basic shapes, complex objects as compositions of basic ones, and transformations. An extensional semantics, which is compositional, is introduced for defining retrieval, classification, and subsumption services. Algorithms exploiting reasoning services, which are sound with respect to the semantics, are also described. Using our logical approach as a formal specification, we implemented a prototype system. A set of experiments, carried out on a testbed of SVG documents to assess the retrieval capabilities of the system, is presented.