This paper presents a solution method for minimizing makespan of a practical large-scale scheduling problem with elastic jobs. The jobs are processed on three servers and restricted by precedence constraints, time windows and capacity limitations. We derive a new method for approximating the server exploitation of the elastic jobs and solve the problem using a tabu search procedure. Finding an initial feasible solution is in general $\mathcal{NP}$-complete, but the tabu search procedure includes a specialized heuristic for solving this problem. The solution method has proven to be very efficient and leads to a significant decrease in makespan compared to the strategy currently implemented.