Many organizations select cloud computing because of their unlimited storage, computation and high bandwidth. Service based Application is composed by number of possibly independent services available in a network which perform the desired functionalities of the architecture. Service-based applications need to dynamically recompose themselves to self-adapt to changing QoS requirements. QoS means performance of the network. Hence, if the application wishes to show a different stage of QoS, it can do so by altering its part of the web services. However, this is not an easy task. Identifying the optimal web service, for each task that the application performs is a hard problem. In this paper, we present a decentralized mechanism for such self-adaptation, using market-based approach. We use a continuous doubleauction to allow applications to decide which services to choose, among the many on offer. We view an application as a multi-agent system and the cloud as a marketplace where many such applications self adapt. We show through a simulation study that our mechanism is effective for the individual application as well as from the collective perspective of all applications adapting at the same time.