Processing streams of data in an overlay network of operators, distributed over a wide-area network, is a common idea shared by dierent applications such as distributed event correlation systems, large-scale sensor networks and distributed reasoning systems. In order to utilize network resources eciently and allow for the deployment of large-scale operator networks, suitable placement algorithms are vital that place operators on physical nodes. In this report, we present a distributed placement algorithm that minimizes the bandwidth-delay product of data streams between operators of the network in order to reduce the induced network load. Since the fundamental optimization problem is NP-hard, we propose a heuristic solution. First, we calculate an optimal solution in an intermediate continuous search space, called latency space. Subsequently the continuous solution is mapped to the physical network. Our evaluations show that this algorithm reduces the resulting network load signi cantly compared to state of the art algorithms and achieves results close to the optimum.