The emergence of electronic marketplaces and other electronic services and applications on the Internet is creating a growing demand for effective management of resources. Due to the nature of the Internet such information changes rapidly. Furthermore, such information must be available for a large number of users and applications, and copies of pieces of information should be stored near the users that need this particular information. In this paper, we present the architecture of MDV, a distributed metadata management system. MDV has a 3-tier architecture and supports caching and replication in the middle-tier so that queries can be evaluated locally. Users and applications specify the information they need and that is replicated using a specialized subscription language. In order to keep replicas up-to-date and initiate the replication of new and relevant information, MDV implements a novel, scalable publish & subscribe algorithm. We describe this algorithm in detail, show how it can be implemented using a standard relational database system, and present the results of performance experiments conducted using our prototype implementation.